| Total: 258
The Automated Essay Scoring (AES) task is an important NLP research problem given its significance for the education ecosystem. Recently, researchers started to apply a hybrid approach to this task. This hybrid approach incorporates into a deep learning model expert features that assess a particular dimension of the essay. Motivated by these successes, we propose to automatically assess essays using a hybrid approach that relies on external discourse knowledge. Our proposed model consists of using transformer-based embeddings to generate semantic representations of essays. Then, we incorporate several discourse features into these representations. Finally, we apply a linear classifier to generate the final score. To evaluate the effectiveness of this approach, we have conducted extensive experiments using the Automated Student Assessment Prize dataset (ASAP). The performance of the proposed model has been evaluated using the Quadratic Weighted Kappa (QWK) metric. The experimental results demonstrate the effectiveness of this approach in comparison with several existing solutions in literature.
Discontinuation rates vary by family planning method and across socio-economic contexts. Understanding these variations and their causes is paramount for developing and implementing policies aimed at curbing discontinuation rates. Randomized controlled trials (RCTs) are ideal for obtaining this information, but this design can be extremely expensive and logistically complex. The ongoing collection of comprehensive data sets, such as Demographic and Health Surveys (DHS data), when combined with machine learning methods, present an alternative and relatively cost-effective means of evidence gathering for policy development. Here, we use causal inference to estimate the effect of injectable contraceptive use on discontinuation over the 12-month period that follows its adoption. To that aim, we use retrospective observational data from seven sub-Saharan African countries captured by the DHS’ Contraceptive Calendar. We use machine learning methods to characterize data regions that share common covariate support. We find that the use of injectables increased the risk of discontinuation in four of the seven countries analyzed. Consistent with existing literature, we find that concerns with the side-effects of injectables appear to be the most frequent reason for discontinuation. However, these risks decreased after adjusting for socio-economic factors. As risk estimates may not apply uniformly within populations, we characterized the sub-populations for robust estimations by their geographical region, level of unmet needs, marital status, level of education, and age of first sex.
Accurate streamflow prediction is critical for ensuring water supply and detecting floods, while also providing essential hydrological inputs for other scientific models in fields such as climate and agriculture. Recently, deep learning models have been shown to achieve state-of-the-art regionalization performance by building a global hydrologic model. These models predict streamflow given catchment physical characteristics and weather forcing data. However, these models are only focused on gauged basins and cannot adapt to ungaugaed basins, i.e., basins without training data. Prediction in Ungauged Basins (PUB) is considered one of the most important challenges in hydrology, as most basins in the United States and around the world have no observations. In this work, we propose a meta-transfer learning approach by enhancing imperfect physics equations that facilitate model adaptation. Intuitively, physical equations can often be used to regularize deep learning models to achieve robust regionalization performance under gauged scenarios, but they can be inaccurate due to the simplified representation of physics. We correct such uncertainty in physical equation by residual approximation and let these corrected equations guide the model training process. We evaluated the proposed method for predicting daily streamflow on the catchment attributes and meteorology for large-sample studies (CAMELS) dataset. The experiment results on hydrological data over 19 years demonstrate the effectiveness of the proposed method in ungauged scenarios.
This paper describes a newly launched project that will produce a new approach to public microtransit for underserved communities. Public microtransit cannot rely on pricing signals to manage demand, and current approaches face the challenges of simultaneously being underutilized and overextended. This project conceives of the setting as a sociotechnical system. Its main idea is to engage users through AI agents in conjunction with platform constraints to find solutions that purely technical conceptions cannot find. The project was specified over an intense series of discussions with key stakeholders (riders, city government, and nongovernmental agencies) and brings together expertise in the disciplines of AI, Operations Research, Urban Planning, Psychology, and Community Development. The project will culminate in a pilot study, results from which will facilitate the transfer of its technology to additional communities.
This paper introduces a novel Functional Graph Convolutional Network (funGCN) framework that combines Functional Data Analysis and Graph Convolutional Networks to address the complexities of multi-task and multi-modal learning in digital health and longitudinal studies. With the growing importance of health solutions to improve health care and social support, ensure healthy lives, and promote well-being at all ages, funGCN offers a unified approach to handle multivariate longitudinal data for multiple entities and ensures interpretability even with small sample sizes. Key innovations include task-specific embedding components that manage different data types, the ability to perform classification, regression, and forecasting, and the creation of a knowledge graph for insightful data interpretation. The efficacy of funGCN is validated through simulation experiments and a real-data application. funGCN source code is publicly available at https://github.com/IBM/funGCN.
Physical inactivity is still a major problem contributing to a growing public health crisis despite a fast-expanding body of technological solutions and wellness research around fitness training. The inaccessibility of professional fitness training remains a leading cause of this gap for reasons encompassing socioeconomic factors, cultural and demographic barriers, and more recently the threat of global pandemics that disrupt traditional modes of staying physically active. Previous lines of work have explored using AI for fitness activity recognition from various sensing modalities such as computer vision, wearable sensors, and force and pressure sensors. However, these works are limited by their feasibility, deployability, and accessibility in real-world scenarios, in addition to the technical challenges faced by each modality for accurate and reliable activity recognition. In this paper, we propose an accessible system for gym activity recognition and correction focusing on foundational fitness activities using ML and a novel pressure sensing mat, and validate its deployability in a real-world use case in a natural gym setting. We present the detailed and previously under-investigated Centre of Pressure (COP) profile of four main gym activities in terms of several COP-related metrics specifically as targets for ML-based recognition tasks. Based on this, we identify COP displacement and COP balance measures as important features for ML-based recognition of these fitness activities for future research in this area. Furthermore, we compare the performance of several ML models in the activity recognition task, achieving 98.5% recognition accuracy using ML models suitable for real-time deployment. Finally, we demonstrate the feasibility of our system in a live real-world with use case in a natural gym environment.
Cities are crucibles of numerous opportunities, but also hotbeds of inequality. The plight of disadvantaged populations who are ``left behind'' within urban environments has been an increasingly pressing concern, which poses substantial threats to the realization of the UN SDG agenda. However, a comprehensive framework for studying this urban dilemma is currently absent, preventing researchers from developing AI models for social good prediction and intervention. To fill this gap, we construct VulnerabilityMap, a framework to meticulously dissect the challenges faced by urban disadvantaged populations, unraveling their vulnerability to a spectrum of shocks and stresses that are categorized through the prism of Maslow's hierarchy of needs. Specifically, we systematically collect large-scale multi-sourced census and web-based data covering more than 328 million people in the United States regarding demographic features, neighborhood environments, offline mobility behaviors, and online social connections. These features are further related to vulnerability outcomes from short-term shocks such as COVID-19 and long-term physiological, social, and self-actualization stresses. Leveraging our framework, we construct machine learning models that exhibit strong performance in predicting vulnerability outcomes from various disadvantage features, which shows the promising utility of our framework to support targeted AI models. Moreover, we provide model-based explainability analysis to interpret the reasons underlying model predictions, shedding light on intricate social factors that trap certain populations inside vulnerable situations. Our constructed dataset is publicly available at https://github.com/LinChen-65/VulnerabilityMap/.
Genomic selection (GS), as a critical crop breeding strategy, plays a key role in enhancing food production and addressing the global hunger crisis. The predominant approaches in GS currently revolve around employing statistical methods for prediction. However, statistical methods often come with two main limitations: strong statistical priors and linear assumptions. A recent trend is to capture the non-linear relationships between markers by deep learning. However, as crop datasets are commonly long sequences with limited samples, the robustness of deep learning models, especially Transformers, remains a challenge. In this work, to unleash the unexplored potential of attention mechanism for the task of interest, we propose a simple yet effective Transformer-based framework that enables end-to-end training of the whole sequence. Via experiments on rice3k and wheat3k datasets, we show that, with simple tricks such as k-mer tokenization and random masking, Transformer can achieve overall superior performance against seminal methods on GS tasks of interest.
Machine learning (ML) bias in mental health detection and analysis is becoming an increasingly pertinent challenge. Despite promising efforts indicating that multimodal methods work better than unimodal methods, there is minimal work on multimodal fairness for depression detection. We propose a causal multimodal framework which consists of two modules. Module 1 performs causal interventional debiasing via backdoor adjustment for each modality to achieve group fairness. Module 2 adaptively fuses the different modalities using a referee-based individual fairness guided fusion mechanism to address individual fairness. We conduct experiments and ablation studies on three depression datasets, D-Vlog, DAIC-WOZ and E-DAIC, and show that our framework improves classification performance as well as group and individual fairness compared to existing approaches.
Achieving gender equality is a pivotal factor in realizing the UN's Global Goals for Sustainable Development. Gender bias studies work towards this and rely on name-based gender inference tools to assign individual gender labels when gender information is unavailable. However, these tools often inaccurately predict gender for Chinese Pinyin names, leading to potential bias in such studies. With the growing participation of Chinese in international activities, this situation is becoming more severe. Specifically, current tools focus on pronunciation (Pinyin) information, neglecting the fact that the latent connections between Pinyin and Chinese characters (Hanzi) behind convey critical information. As a first effort, we formulate the Pinyin name-gender guessing problem and design a Multi-Task Learning Network assisted by Knowledge Distillation that enables the Pinyin representations in the model to possess semantic features of Chinese characters and to learn gender information from Chinese character names. Our open-sourced method surpasses commercial name-gender guessing tools by 9.70% to 20.08% relatively, and also outperforms the state-of-the-art algorithms.
This paper makes three contributions. First, it presents a generalizable, novel framework dubbed toxicity rabbit hole that iteratively elicits toxic content from a wide suite of large language models. Spanning a set of 1,266 identity groups, we first conduct a bias audit of PaLM 2 guardrails presenting key insights. Next, we report generalizability across several other models. Through the elicited toxic content, we present a broad analysis with a key emphasis on racism, antisemitism, misogyny, Islamophobia, homophobia, and transphobia. We release a massive dataset of machine-generated toxic content with a view toward safety for all. Finally, driven by concrete examples, we discuss potential ramifications.
Proper attire is a professional requirement for teachers and teachers' dress influence students' perceptions of teacher quality. Therefore, evaluating teacher attire can better regulate and improve the teacher’s dress. However, the lack of a dataset on teacher attire hinders the development of this field. For this purpose, this paper constructs a Teachers' Classroom Dress Assessment (TCDA) dataset. To our knowledge, it is the first dataset focused on teacher attire. This dataset is entirely from the classroom environment, covering 25 teacher attributes, with a total of 11879 teacher dress samples and sufficient positive and negative examples. Therefore, the TCDA dataset is a challenging evaluation dataset with characteristics such as data diversity. In order to verify the effectiveness of the dataset, this paper systematically explores a new perspective on human attribute information and proposes for the first time a Teachers' Dress Assessment Method (TDAM), aiming to use predicted teacher attributes to scoring the overall attire of each teacher, thereby promoting the development of the teacher's classroom teaching field. The experimental results demonstrate the rationality of the TCDA dataset and the effectiveness of the TDAM method. The dataset and code can be openly obtained at https://github.com/MingZier/TCDA-dataset.
The air quality inference problem aims to utilize historical data from a limited number of observation sites to infer the air quality index at an unknown location. Considering the sparsity of data due to the high maintenance cost of the stations, good inference algorithms can effectively save the cost and refine the data granularity. While spatio-temporal graph neural networks have made excellent progress on this problem, their non-Euclidean and discrete data structure modeling of reality limits its potential. In this work, we make the first attempt to combine two different spatio-temporal perspectives, fields and graphs, by proposing a new model, Spatio-Temporal Field Neural Network, and its corresponding new framework, Pyramidal Inference. Extensive experiments validate that our model achieves state-of-the-art performance in nationwide air quality inference in the Chinese Mainland, demonstrating the superiority of our proposed model and framework.
Predicting the spatiotemporal variation in streamflow along with uncertainty quantification enables decision-making for sustainable management of scarce water resources. Process-based hydrological models (aka physics-based models) are based on physical laws, but use simplifying assumptions which can lead to poor accuracy. Data-driven approaches offer a powerful alternative, but they require large amount of training data and tend to produce predictions that are inconsistent with physical laws. This paper studies a constrained reasoning and learning (CRL) approach where physical laws represented as logical constraints are integrated as a layer in the deep neural network. To address small data setting, we develop a theoretically-grounded training approach to improve the generalization accuracy of deep models. For uncertainty quantification, we combine the synergistic strengths of Gaussian processes (GPs) and deep temporal models by passing the learned latent representation as input to a standard distance-based kernel. Experiments on multiple real-world datasets demonstrate the effectiveness of both CRL and GP with deep kernel approaches over strong baseline methods.
The escalating prevalence of cannabis use, and associated cannabis-use disorder (CUD), poses a significant public health challenge globally. With a notably wide treatment gap, especially among emerging adults (EAs; ages 18-25), addressing cannabis use and CUD remains a pivotal objective within the 2030 United Nations Agenda for Sustainable Development Goals (SDG). In this work, we develop an online reinforcement learning (RL) algorithm called reBandit which will be utilized in a mobile health study to deliver personalized mobile health interventions aimed at reducing cannabis use among EAs. reBandit utilizes random effects and informative Bayesian priors to learn quickly and efficiently in noisy mobile health environments. Moreover, reBandit employs Empirical Bayes and optimization techniques to autonomously update its hyper-parameters online. To evaluate the performance of our algorithm, we construct a simulation testbed using data from a prior study, and compare against commonly used algorithms in mobile health studies. We show that reBandit performs equally well or better than all the baseline algorithms, and the performance gap widens as population heterogeneity increases in the simulation environment, proving its adeptness to adapt to diverse population of study participants.
Inland water quality monitoring is vital for clean water access and aquatic ecosystem management. Remote sensing machine learning models enable large-scale observations, but are difficult to train due to data scarcity and variability across many lakes. Multi-task learning approaches enable learning of lake differences by learning multiple lake functions simultaneously. However, they suffer from a trade-off between parameter efficiency and the ability to model task differences flexibly, and struggle to model many diverse lakes with few samples per task. We propose Multi-Task Hypernetworks, a novel multi-task learning architecture which circumvents this trade-off using a shared hypernetwork to generate different network weights for each task from small task-specific embeddings. Our approach stands out from existing works by providing the added capacity to leverage task-level metadata, such as lake depth and temperature, explicitly. We show empirically that Multi-Task Hypernetworks outperform existing multi-task learning architectures for water quality remote sensing and other tabular data problems, and leverages metadata more effectively than existing methods.
Wearable devices are being increasingly used in high-impact health applications including vital sign monitoring, rehabilitation, and movement disorders. Wearable health monitoring can aid in the United Nations social development goal of healthy lives by enabling early warning, risk reduction, and management of health risks. Health tasks on wearable devices employ multiple sensors to collect relevant parameters of user’s health and make decisions using machine learning (ML) algorithms. The ML algorithms assume that data from all sensors are available for the health monitoring tasks. However, the applications may encounter missing or incomplete data due to user error, energy limitations, or sensor malfunction. Missing data results in significant loss of accuracy and quality of service. This paper presents a novel Classifier-Aware iMputation (CAM) approach to impute missing data such that classifier accuracy for health tasks is not affected. Specifically, CAM employs unsupervised clustering followed by a principled search algorithm to uncover imputation patterns that maintain high accuracy. Evaluations on seven diverse health tasks show that CAM achieves accuracy within 5% of the baseline with no missing data when one sensor is missing. CAM also achieves significantly higher accuracy compared to generative approaches with negligible energy overhead, making it suitable for wide range of wearable applications.
Intimate Partner Violence (IPV) is a global problem affecting more than 2 billion women worldwide. Our paper makes two key contributions. First, via a substantial corpus of 53,220 comments to 1,563 Intimate Partner Physical Violence (IPPV) posts gleaned from more than 10 million comments posted on 523,232 posts on a popular parental health website in Iran, we present the first-ever computational analysis of user comments on accounts of IPPV in Iran. We harness large language models and participatory AI and tackle extreme class imbalance and other linguistic challenges that arise from tackling low-resource languages to shed light on the gender struggles of a country with documented stark gender inequality. With active input from a woman with a history of advocacy for social rights and grounded in Iranian culture, we characterize comments on IPPV into three broad categories: empathy, confront, and conform, and analyze their distribution. Second, we release an important dataset of 3,400 comments on IPPV posts.
New Zealand's unique ecosystems face increasing threats from climate change, impacting biodiversity and posing challenges to safety, livelihoods, and well-being. To tackle these complex issues, advanced data science and artificial intelligence techniques can provide unique solutions. Currently, in its fourth year of a seven-year program, TAIAO focuses on methods for analyzing environmental datasets. Recognizing this urgency, the open-source TAIAO platform was developed. This platform enables new artificial intelligence research for environmental data and offers an open-access repository to enhance reproducibility in the field. This paper will showcase four environmental case studies, artificial intelligence research, platform implementation details, and future development plans.
Urban migration is a significant aspect of a city's economy. The exploration of the underlying determinants of housing purchases among current residents contributes to the study of future trends in urban migration, enabling governments to formulate appropriate policies to guide future economic growth. This article employs a factor model to analyze data on residents' rentals, first-time home purchases, and subsequent housing upgrades. We decompose the factors influencing housing purchases into common drivers and specific drivers. Our hypothesis is that common drivers reflect universal social patterns, while personalized drivers represent stochastic elements. We construct a correlation matrix capturing the inter-resident relationships based on the common drivers of housing purchases. We then propose a graph neural network based on the correlation matrix to model housing predictions as a node classification problem. Our model addresses two critical questions. Firstly, we aim to identify which part of rental residents will engage in first-time home purchases in the future. Secondly, we seek to determine which group of residents, having completed rental and first-time home purchases, will opt for a second home purchase. The results of our testing on real-world datasets demonstrate that based solely on rental and home purchase records, we can achieve a sensitivity for housing predictions exceeding 80%.
Trajectory prediction is a cornerstone in autonomous driving (AD), playing a critical role in enabling vehicles to navigate safely and efficiently in dynamic environments. To address this task, this paper presents a novel trajectory prediction model tailored for accuracy in the face of heterogeneous and uncertain traffic scenarios. At the heart of this model lies the Characterized Diffusion Module, an innovative module designed to simulate traffic scenarios with inherent uncertainty. This module enriches the predictive process by infusing it with detailed semantic information, thereby enhancing trajectory prediction accuracy. Complementing this, our Spatio-Temporal (ST) Interaction Module captures the nuanced effects of traffic scenarios on vehicle dynamics across both spatial and temporal dimensions with remarkable effectiveness. Demonstrated through exhaustive evaluations, our model sets a new standard in trajectory prediction, achieving state-of-the-art (SOTA) results on the Next Generation Simulation (NGSIM), Highway Drone (HighD), and Macao Connected Autonomous Driving (MoCAD) datasets across both short and extended temporal spans. This performance underscores the model's unparalleled adaptability and efficacy in navigating complex traffic scenarios, including highways, urban streets, and intersections.
Traditional traffic prediction, limited by the scope of sensor data, falls short in comprehensive traffic management. Mobile networks offer a promising alternative using network activity counts, but these lack crucial directionality. Thus, we present the TeltoMob dataset, featuring undirected telecom counts and corresponding directional flows, to predict directional mobility flows on roadways. To address this, we propose a two-stage spatio-temporal graph neural network (STGNN) framework. The first stage uses a pre-trained STGNN to process telecom data, while the second stage integrates directional and geographic insights for accurate prediction. Our experiments demonstrate the framework's compatibility with various STGNN models and confirm its effectiveness. We also show how to incorporate the framework into real-world transportation systems, enhancing sustainable urban mobility.
Urban villages are areas filled with rural-like improvised structures in Chinese cities, usually housing the most vulnerable groups. Under the guidance of the Sustainable Development Goals (SDGs), the Chinese government initiated renewal and redevelopment projects, underscoring the meticulous mapping and segmentation of urban villages. Satellite imagery is advanced and efficient in identifying urban villages and monitoring changes, but traditional methods neglect the morphological diversity in season, shape, size, spacing, and layout of urban villages, which is not satisfying for long-term wide-range data. Here, we design a targeted approach based on Tobler’s First Law of Geography, using curriculum labeling to solve morphological diversity and semi-automatically generate segmentation for urban village boundaries. Specifically, we use manually labeled data as seeds for pre-trained SegFormer models and incrementally fine-tune the model based on geographical proximity. The rigorous experimentation across five diverse cities substantiates the commendable efficacy of our methodology. IoU metric demonstrates a noteworthy improvement of over 119% to baseline. Our final results cover 265,050 urban villages across 433 cities in China over the past 10 years, and the analysis reveals the uneven redevelopment by geography and city scale. We further examine the within-city distribution and verify the urban scaling law associated with several socio-economic factors. Our method can be used nationwide to decide redevelopment priority and resource tilt, contributing to SDG 11.1 on affordable housing and upgrading slums. The code and dataset are available at https://github.com/tsinghua-fib-lab/LtCUV.
Opioid overdose is an escalating global epidemic, affecting 16 million individuals. Lack of overdose detection and slower response times are the leading causes of overdose deaths. During a fatal opioid overdose, the user exhibits motionlessness, lack of breathing, and hypoxemia (oxygen saturation drops). In this paper, we discuss the development of a shoulder-based wearable overdose detection device that monitors hypoxemia, motion, and respiration. The device's design considers the underserved socio-economic population and their psychological contexts. However, conventional approaches to detecting an overdose typically focus on a single biomarker. To address this, we have developed a robust capsule networks based machine learning (ML) model, OxyCaps that integrates oxygen saturation, respiration rate, and motion to classify different levels of hypoxemia. This also helps improve patient adherence by decreasing the chances of false positive alerts. To determine a hypoxemic state, the model considers various features like skin tone, body physiology, motion, and photoplethysmography (PPG) signals. In the absence of real-world opioid overdose data, our research leverages data collected by our device from 19 patients experiencing sleep apnea, exploiting the parallels between overdose and apnea biomarkers. Our dataset provides a novel compilation of raw PPG and motion signals detected from the shoulder. Our model classifies 3 stages of hypoxemia with an average accuracy of 92%, specifically achieving a high recall of 0.98 for the critical hypoxemic state that is crucial in determining an overdose.
Hierarchical leaf vein segmentation is a crucial but under-explored task in agricultural sciences, where analysis of the hierarchical structure of plant leaf venation can contribute to plant breeding. While current segmentation techniques rely on data-driven models, there is no publicly available dataset specifically designed for hierarchical leaf vein segmentation. To address this gap, we introduce the HierArchical Leaf Vein Segmentation (HALVS) dataset, the first public hierarchical leaf vein segmentation dataset. HALVS comprises 5,057 real-scanned high-resolution leaf images collected from three plant species: soybean, sweet cherry, and London planetree. It also includes human-annotated ground truth for three orders of leaf veins, with a total labeling effort of 83.8 person-days. Based on HALVS, we further develop a label-efficient learning paradigm that leverages partial label information, i.e. missing annotations for tertiary veins. Empirical studies are performed on HALVS, revealing new observations, challenges, and research directions on leaf vein segmentation. Our dataset and code are available at https://github.com/WeizhenLiuBioinform/ HALVS-Hierarchical-Vein-Segment.